The official PyTorch implementation of CVPR 2020 paper "Interactive Image Segmentation with First Click Attention".

• PyTorch>=0.4.1
• Opencv
• Scipy
• Matplotlib

Put the pretrained model into the created folder "pretrained_model" and the unzipped datasets into the created folder "dataset".

python evaluate.py --backbone [resnet,res2net] --dataset [GrabCut,Berkeley,DAVIS,VOC2012] (--sis) 

python annotator.py --backbone [resnet,res2net] --input test.jpg --output test_mask.jpg (--sis)

([x,y,z] means choices. (x) means optional.)

• GrabCut ( GoogleDrive | BaiduYun pwd: 6qkj )
• Berkeley ( GoogleDrive | BaiduYun pwd: 6bfw )
• DAVIS ( GoogleDrive | BaiduYun pwd: u5vd )
  (The three datasets we used are downloaded from f-BRS)
• PASCAL ( official )

• fcanet-resnet ( GoogleDrive | BaiduYun pwd: g989 )
• fcanet-res2net ( GoogleDrive | BaiduYun pwd: xzmx )

If you find this work or code is helpful in your research, please cite:

@inproceedings{fClick20CVPR,
 title={Interactive Image Segmentation with First Click Attention},
 author={Zheng Lin and Zhao Zhang and Lin-Zhuo Chen and Ming-Ming Cheng and Shao-Ping Lu},
 booktitle={IEEE CVPR},
 year={2020},
}

If you have any questions, feel free to contact me via: frazer.linzheng(at)gmail.com.